In [81]:
%load_ext autoreload
%autoreload 2
In [138]:
import os
MOMAPS_HOME = '/home/labs/hornsteinlab/Collaboration/MOmaps'
LOGS_PATH = os.path.join(MOMAPS_HOME, 'src', 'preprocessing', 'logs','deltaNLS')
PLOT_PATH = os.path.join(MOMAPS_HOME, 'src', 'preprocessing', 'notebooks','figures','delta_NLS')
os.chdir(MOMAPS_HOME)
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
sns.set(style="whitegrid", font_scale=1.5)
sns.color_palette("husl", 8)
plt.rcParams["image.cmap"] = "Set1"
from tqdm.notebook import tqdm
from src.common.lib.preprocessing_utils import rescale_intensity
from src.common.lib.images_qc import *
sys.path.insert(1, "/home/labs/hornsteinlab/Collaboration/MOmaps_Sagy/MOmaps/src/common/lib")
import contextlib
import io
import matplotlib
import warnings
warnings.filterwarnings('ignore', category=pd.core.common.SettingWithCopyWarning)
from src.common.lib.qc_config_tmp import *
In [109]:
df = log_files_qc(LOGS_PATH)
validate folder structure and files existence¶
In [96]:
# choose batches
batches = [f'batch{i}' for i in range (2,6)]
#batches=['batch5']
Raw Files¶
In [97]:
root_directory_raw = os.path.join(MOMAPS_HOME, 'input', 'images', 'raw', 'SpinningDisk','deltaNLS_sort')
batches_raw = [batch.replace("_16bit","") for batch in batches]
raws = run_validate_folder_structure(root_directory_raw, False, dnls_panels, dnls_markers,PLOT_PATH,
dnls_marker_info,dnls_cell_lines_to_cond, reps, dnls_cell_lines_for_disp,
dnls_expected_dapi_raw, batches=batches_raw,fig_width=4, fig_height=10)
Processed¶
In [98]:
root_directory_proc = os.path.join(MOMAPS_HOME, 'input', 'images', 'processed', 'spd2',
'SpinningDisk','deltaNLS')
procs = run_validate_folder_structure(root_directory_proc, True, dnls_panels, dnls_markers,PLOT_PATH,
dnls_marker_info,dnls_cell_lines_to_cond, reps, dnls_cell_lines_for_disp,
dnls_expected_dapi_raw, batches=batches_raw, fig_width=4, fig_height=10)
Difference between Raw and Processed¶
In [100]:
display_diff(batches, raws, procs, PLOT_PATH, 10,4)
In [101]:
for batch in batches:
with contextlib.redirect_stdout(io.StringIO()):
var = sample_and_calc_variance(root_directory_proc, batch, sample_size_per_markers=200, num_markers=26)
print(f'{batch} var: ',var)
Number of sites in each batch and cell line ¶
In [119]:
plot_sites_count(df, dnls_expected_raw, dnls_lines_order, dnls_custom_palette, split_to_reps=True)
Number of Cells in Site for each batch and cell line ¶
In [120]:
df_no_empty_sites = df[df.n_valid_tiles !=0]
plot_cell_count(df_no_empty_sites, dnls_lines_order, dnls_custom_palette, whole_cells=True)
plot_cell_count(df_no_empty_sites, dnls_lines_order, dnls_custom_palette, whole_cells=False)
# can add norm=True to norm by max
number of valid tiles per image (site)¶
In [131]:
plot_n_valid_tiles_count(df, custom_palette, reps, batch_min=2, batch_max=5)
Heatmap QC per batch, panel and cell line(tiles that passed QC condition) ¶
In [142]:
plot_hm(df, split_by='rep', rows='cell_line', columns='panel', fig_height=2)
Assessing Staining Reproducibility and Outliers¶
In [190]:
dnls_cell_lines_for_disp
Out[190]:
In [182]:
Out[182]:
In [208]:
# for batch in [batches[0]]:
# print(batch)
# raw_df = run_calc_hist_new(f'deltaNLS_sort/{batch}',dnls_cell_lines_for_disp,
# dnls_markers,num_markers=((len(dnls_markers)-1)+dnls_panels.shape[1])*2,
# show_cond=True,sample_size_per_markers=2)
# print("="*30)
In [ ]:
print(os.system('pwd'))
print("Done!")
In [ ]:
# save notebook as HTML ( the HTML will be saved in the same folder the original script is)
from IPython.display import display, Javascript
display(Javascript('IPython.notebook.save_checkpoint();'))
os.system('jupyter nbconvert --to html src/preprocessing/notebooks/cell_count_stats_analysis_dnls.ipynb')
In [ ]: